BeautifulSoup库测试代码

import requests
from bs4 import BeautifulSoup
import time

headers={    
    #'User-Agent':'Nokia6600/1.0 (3.42.1) SymbianOS/7.0s Series60/2.0 Profile/MIDP-2.0 Configuration/CLDC-1.0'
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
def get_info(url):
    res=requests.get(url,headers=headers)
    soup=BeautifulSoup(res.text,'lxml')
    aa=soup.select('span.pc_temp_num')[0]
    for a in aa:
        a=aa.get_text().strip()
        print(a)


if __name__=='__main__':
    urls=['http://www.kugou.com/yy/rank/home/{}-8888.html?from=homepage'.format(str(i)) for i in range(3,4)]
    for url in urls:
        get_info(url)
        time.sleep(1)

 

posted @ 2018-04-16 11:05  蓝勃斐重新开始  阅读(145)  评论(0编辑  收藏  举报